{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:42:55Z","timestamp":1767339775646,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T00:00:00Z","timestamp":1626307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T00:00:00Z","timestamp":1626307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T00:00:00Z","timestamp":1626307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,15]]},"DOI":"10.1109\/rcar52367.2021.9517647","type":"proceedings-article","created":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T20:32:50Z","timestamp":1630441970000},"page":"1425-1431","source":"Crossref","is-referenced-by-count":2,"title":["Data-efficient Deep Reinforcement Learning Method Toward Scaling Continuous Robotic Task with Sparse Rewards"],"prefix":"10.1109","author":[{"given":"Junkai","family":"Ren","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixing","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","first-page":"6818","article-title":"Imitation learning from imperfect demonstration","author":"wu","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI.2017.45"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref12","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"0","journal-title":"Proceedings of the Conference on Robot Learning (CoRL)"},{"key":"ref13","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proceedings of the Neural Information Processing Systems (NeurIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref15","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"fu","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref16","first-page":"254","article-title":"Methodologies for imitation learning via inverse reinforcement learning: a review[J]","volume":"56","author":"kaifeng","year":"2019","journal-title":"Journal of Computer research and development"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00313"},{"key":"ref18","article-title":"Prioritized experience replay[J]","author":"schaul","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research[J]","author":"plappert","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref28","first-page":"1856","article-title":"Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref27","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref3","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics","author":"mosavi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2543000"},{"key":"ref5","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref7","article-title":"Survey on reinforcement learning for language processing[J]","author":"uc-cetina","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.148"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref22","first-page":"1321","article-title":"V-rep: A versatile and scalable robot simulation framework","author":"rohmer","year":"0","journal-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"ref21","article-title":"Pyrep: Bringing v-rep to deep robot learning[J]","author":"james","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref23","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref25","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"}],"event":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","start":{"date-parts":[[2021,7,15]]},"location":"Xining, China","end":{"date-parts":[[2021,7,19]]}},"container-title":["2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9517075\/9517076\/09517647.pdf?arnumber=9517647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:45:05Z","timestamp":1652197505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9517647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,15]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/rcar52367.2021.9517647","relation":{},"subject":[],"published":{"date-parts":[[2021,7,15]]}}}